{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M75D7QOJDRYTQC7IBVLBIJT3C4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f7762047576fc991a3b0f904dc86bd0112aa2969fa1efb7198cbb48355a161cf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:07:49Z","title_canon_sha256":"96bf3addbff70c662825aacc1463d253333fe5bf3fef592cc0e696222a7d45ca"},"schema_version":"1.0","source":{"id":"2406.09329","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09329","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09329v2","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09329","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"M75D7QOJDRYT","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"M75D7QOJDRYTQC7I","created_at":"2026-07-05T09:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"M75D7QOJ","created_at":"2026-07-05T09:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:289b29ba670a485a11f066ead49201ba681ae3f3b990237074f1e2b0e1f5d8c3","target":"graph","created_at":"2026-07-05T09:27:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.09329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While imitation learning requires access to high-quality data, offline reinforcement learning (RL) should, in principle, perform similarly or better with substantially lower data quality by using a value function. However, current results indicate that offline RL often performs worse than imitation learning, and it is often unclear what holds back the performance of offline RL. Motivated by this observation, we aim to understand the bottlenecks in current offline RL algorithms. While poor performance of offline RL is typically attributed to an imperfect value function, we ask: is the main bott","authors_text":"Aviral Kumar, Kevin Frans, Seohong Park, Sergey Levine","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:07:49Z","title":"Is Value Learning Really the Main Bottleneck in Offline RL?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09329","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11ec327307bbfc788e373b88d61d44579eefb4150d038dc4027d2bad033dd31a","target":"record","created_at":"2026-07-05T09:27:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f7762047576fc991a3b0f904dc86bd0112aa2969fa1efb7198cbb48355a161cf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:07:49Z","title_canon_sha256":"96bf3addbff70c662825aacc1463d253333fe5bf3fef592cc0e696222a7d45ca"},"schema_version":"1.0","source":{"id":"2406.09329","kind":"arxiv","version":2}},"canonical_sha256":"67fa3fc1c91c71380be80d5614267b1700893e99ccd7cdac14ed0489ca962e81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67fa3fc1c91c71380be80d5614267b1700893e99ccd7cdac14ed0489ca962e81","first_computed_at":"2026-07-05T09:27:23.131608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:23.131608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CrpYV2vXXYPG0OX3gY5IK+CI1ABhreciMRRj3THniM6wEOIhnFEiha7/oyXbI+L5b88vd6ZI2GeRpCCLcwQtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:23.132083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09329","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ec327307bbfc788e373b88d61d44579eefb4150d038dc4027d2bad033dd31a","sha256:289b29ba670a485a11f066ead49201ba681ae3f3b990237074f1e2b0e1f5d8c3"],"state_sha256":"1795aa07874ede210e9a51cc8ceaaf376b4ffd903d837ce651b3ba0b0d3f033d"}